A study on with the bottom-up and the top-down procedure in hierarchical neural networks

Author

Iwasaki, Masahiro ; Hashiyama, Tomonori ; Okuma, Shigeru

Author_Institution

Dept. of Electron., Nagoya Univ., Japan

Volume

5

fYear

1997

fDate

12-15 Oct 1997

Firstpage

4041

Abstract

This paper presents a new framework for hierarchical neural networks. It is based on the interaction between bottom-up and topdown procedure to realize human-like cognitive processes. The proposed system consists of 3 layers, input layer, feature extraction layer and symbol layer. Input layer is a kind of associative memory and associate by itself. When the association fails, feature extraction through bottom-up procedure and attention to the parts of input pattern through top-down procedure make it possible to associate target pattern. Some simulation results show the feasibility of proposed system

Keywords

associative processing; content-addressable storage; feature extraction; hierarchical systems; neural nets; associative memory; cognitive processes; feature extraction; feature extraction layer; hierarchical neural networks; input layer; symbol layer; Biological neural networks; Electronic mail; Electronics industry; Feature extraction; Humans; Industrial electronics; Intelligent networks; Neural networks; Neurons; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on

Conference_Location

Orlando, FL

ISSN

1062-922X

Print_ISBN

0-7803-4053-1

Type

conf

DOI

10.1109/ICSMC.1997.637318

Filename

637318